Dependency parsing representation effects on the accuracy of semantic applications — an example of an inflective language
Lauma Pretkalniņa, Artūrs Znotiņš, Laura Rituma, Didzis Goško
Abstract
In this paper we investigate how different dependency representations of a treebank influence the accuracy of the dependency parser trained on this treebank and the impact on several parser applications: named entity recognition, coreference resolution and limited semantic role labeling. For these experiments we use Latvian Treebank, whose native annotation format is dependency based hybrid augmented with phrase-like elements. We explore different representations of coordinations, complex predicates and punctuation mark attachment. Our experiments shows that parsers trained on the variously transformed treebanks vary significantly in their accuracy, but the best-performing parser as measured by attachment score not always leads to best accuracy for an end application.- Anthology ID:
- L14-1676
- Volume:
- Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)
- Month:
- May
- Year:
- 2014
- Address:
- Reykjavik, Iceland
- Venue:
- LREC
- SIG:
- Publisher:
- European Language Resources Association (ELRA)
- Note:
- Pages:
- 4074–4081
- Language:
- URL:
- http://www.lrec-conf.org/proceedings/lrec2014/pdf/879_Paper.pdf
- DOI:
- Cite (ACL):
- Lauma Pretkalniņa, Artūrs Znotiņš, Laura Rituma, and Didzis Goško. 2014. Dependency parsing representation effects on the accuracy of semantic applications — an example of an inflective language. In Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14), pages 4074–4081, Reykjavik, Iceland. European Language Resources Association (ELRA).
- Cite (Informal):
- Dependency parsing representation effects on the accuracy of semantic applications — an example of an inflective language (Pretkalniņa et al., LREC 2014)
- PDF:
- http://www.lrec-conf.org/proceedings/lrec2014/pdf/879_Paper.pdf